Affordable Access

Access to the full text

An Adaptive Neuro-fuzzy Inference System for Robot Handling Fabrics with Curved Edges towards Sewing

Authors
  • Zacharia, Paraskevi Th.1
  • 1 University of Patras, Department of Mechanical Engineering and Aeronautics, Patras, Greece , Patras (Greece)
Type
Published Article
Journal
Journal of Intelligent & Robotic Systems
Publisher
Springer-Verlag
Publication Date
Sep 03, 2009
Volume
58
Issue
3-4
Pages
193–209
Identifiers
DOI: 10.1007/s10846-009-9362-6
Source
Springer Nature
Keywords
License
Yellow

Abstract

This paper presents the design of a neuro-fuzzy visual servoing controller for robot guiding fabrics with curved edges towards sewing. Fabrics comprising real cloths consist of curved edges of arbitrary curvatures that can not be standardized. To overcome this difficulty, the idea is to train the robot sewing system and to apply this methodology in a real-time operation environment. The proposed approach for robot sewing is based on visual servoing and a learning technique that combines neural networks and fuzzy logic. A novel genetic-oriented clustering method is used to construct the initial FIS models and then, adaptive neuro-fuzzy inference systems allow tuning them so that it is possible to obtain better estimates. Extensive experiments were carried out in order to build data sets using fabrics with curved edges of various curvatures. The proposed model is validated using fabrics that had not been included in the training process and the results demonstrate that the proposed approach is efficient and effective for robot guiding fabrics with arbitrary curved edges towards sewing.

Report this publication

Statistics

Seen <100 times